Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer

Dataset: Open Web Text

Neuron 898 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gpt2-small')

Click the toggle to see the full text!

Text #0

Max Range: 1.7644. Min Range: -1.7644

Max Act: 1.7644. Min Act: -0.1700

Data Index: 3561647 (Open Web Text)

Max Activating Token Index: 402

Text #1

Max Range: 1.7644. Min Range: -1.7644

Max Act: 1.7526. Min Act: -0.1700

Data Index: 144170 (Open Web Text)

Max Activating Token Index: 91

Text #2

Max Range: 1.7644. Min Range: -1.7644

Max Act: 1.7465. Min Act: -0.1700

Data Index: 2729859 (Open Web Text)

Max Activating Token Index: 804

Text #3

Max Range: 1.7644. Min Range: -1.7644

Max Act: 1.7457. Min Act: -0.1700

Data Index: 4257044 (Open Web Text)

Max Activating Token Index: 456

Text #4

Max Range: 1.7644. Min Range: -1.7644

Max Act: 1.7276. Min Act: -0.1700

Data Index: 8337527 (Open Web Text)

Max Activating Token Index: 166

Text #5

Max Range: 1.7644. Min Range: -1.7644

Max Act: 1.7267. Min Act: -0.1700

Data Index: 5630239 (Open Web Text)

Max Activating Token Index: 860

Text #6

Max Range: 1.7644. Min Range: -1.7644

Max Act: 1.7219. Min Act: -0.1700

Data Index: 3913634 (Open Web Text)

Max Activating Token Index: 904

Text #7

Max Range: 1.7644. Min Range: -1.7644

Max Act: 1.7109. Min Act: -0.1700

Data Index: 5987076 (Open Web Text)

Max Activating Token Index: 339

Text #8

Max Range: 1.7644. Min Range: -1.7644

Max Act: 1.6990. Min Act: -0.1700

Data Index: 5375008 (Open Web Text)

Max Activating Token Index: 440

Text #9

Max Range: 1.7644. Min Range: -1.7644

Max Act: 1.6800. Min Act: -0.1700

Data Index: 2810031 (Open Web Text)

Max Activating Token Index: 910

Text #10

Max Range: 1.7644. Min Range: -1.7644

Max Act: 1.6913. Min Act: -0.1700

Data Index: 8183053 (Open Web Text)

Max Activating Token Index: 446

Text #11

Max Range: 1.7644. Min Range: -1.7644

Max Act: 1.6927. Min Act: -0.1700

Data Index: 5412510 (Open Web Text)

Max Activating Token Index: 962

Text #12

Max Range: 1.7644. Min Range: -1.7644

Max Act: 1.6947. Min Act: -0.1700

Data Index: 6828975 (Open Web Text)

Max Activating Token Index: 432

Text #13

Max Range: 1.7644. Min Range: -1.7644

Max Act: 1.6727. Min Act: -0.1700

Data Index: 146773 (Open Web Text)

Max Activating Token Index: 855

Text #14

Max Range: 1.7644. Min Range: -1.7644

Max Act: 1.6875. Min Act: -0.1700

Data Index: 4348691 (Open Web Text)

Max Activating Token Index: 163

Text #15

Max Range: 1.7644. Min Range: -1.7644

Max Act: 1.6791. Min Act: -0.1700

Data Index: 8819781 (Open Web Text)

Max Activating Token Index: 42

Text #16

Max Range: 1.7644. Min Range: -1.7644

Max Act: 1.6896. Min Act: -0.1700

Data Index: 4734928 (Open Web Text)

Max Activating Token Index: 462

Text #17

Max Range: 1.7644. Min Range: -1.7644

Max Act: 1.6719. Min Act: -0.1700

Data Index: 7550836 (Open Web Text)

Max Activating Token Index: 958

Text #18

Max Range: 1.7644. Min Range: -1.7644

Max Act: 1.6734. Min Act: -0.1700

Data Index: 3828270 (Open Web Text)

Max Activating Token Index: 415

Text #19

Max Range: 1.7644. Min Range: -1.7644

Max Act: 1.6733. Min Act: -0.1700

Data Index: 7977956 (Open Web Text)

Max Activating Token Index: 865